© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162292
    Prev
    Next
    INDEX
    Explanations

    opposites attract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    1.16
    ш
    1.16
    quela
    1.09
    со
    1.05
    то
    1.04
    лий
    1.03
    ية
    1.02
    вер
    1.02
    ку
    1.01
    örungen
    1.01
    POSITIVE LOGITS
    on
    1.45
     by
    1.38
    "
    1.32
    od
    1.30
     in
    1.19
    सी
    1.19
    も
    1.18
     war
    1.14
    Ս
    1.13
    डी
    1.12
    Activations Density 0.000%

    No Known Activations